© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47516
    Prev
    Next
    INDEX
    Explanations

    ancestry and genealogy services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     legend
    -0.82
     legends
    -0.79
    .</
    -0.77
    quise
    -0.73
     eje
    -0.72
     germs
    -0.72
    ഥ
    -0.71
    Filmografie
    -0.70
     alarm
    -0.69
    ksessa
    -0.68
    POSITIVE LOGITS
     Ancestry
    2.81
     ancestry
    2.63
    Roots
    1.90
    cestry
    1.82
     Roots
    1.82
    ances
    1.73
    roots
    1.63
     genealogy
    1.52
     ancest
    1.48
     roots
    1.47
    Activations Density 0.059%

    No Known Activations